• Anirban Chakraborty
• Sai Sowjanya Kallempudi
• Ruchika

This paper deals with many literature reviews on Deep Neural Network. In the field of biometrics, authentication and access-control and compliance, digital card and surveillance systems, face recognition (FR), identifying the procedure of human beings using facial imagery, is a multitude of hands-on applications. Convolutionary neural networks (CovNets) have proven to be successful for FR, a form of deep networks. Some preprocessing steps such as sampling must be taken for real-time systems before use in CovNets. Nevertheless, then full images are also transferred (all pixel values) to CovNets as a input and all steps performed by the network (feature collection, function filtering, training). That is why CovNets are often difficult and time-taking to implement. CovNets are in the growing stages, with very small accuracies, so they have high future scope. This paper offers a new sight of utilizing a deep neural network for facial recognition. In this approach facial features which are extracted are provided in place of providing raw pixel values as input. This reduces the difficulty and gives the Yale faces dataset accuracy of 97.05%.

Put your keywords here, keywords are separated by comma.

"Deep Neural Networks In A General Perspective", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.230-234, November 2018, Available :http://www.jetir.org/papers/JETIRDR06035.pdf

"Deep Neural Networks In A General Perspective", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp230-234, November 2018, Available at : http://www.jetir.org/papers/JETIRDR06035.pdf